Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    contractions and possessives marked by apostrophes in conversational text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @theofarrell99
    New Auto-Interp
    Negative Logits
    8
    1.24
     Cerr
    1.12
    6
    1.06
    7
    1.03
    ToStr
    1.00
     całkow
    0.99
     Cielo
    0.98
     Pelle
    0.98
     Cd
    0.97
     Berman
    0.96
    POSITIVE LOGITS
     OneDrive
    1.12
     organisers
    1.11
     (£
    1.10
     Hy
    1.08
     calendrier
    1.07
     antibiotic
    1.05
     hy
    1.04
     erros
    1.02
     impresses
    1.02
     hygiene
    1.00
    Act Density 2.911%

    No Known Activations